Skripsi

PENDETEKSIAN PENDARAHAN PADA CITRA DIGITAL RADIOLOGI OTAK MANUSIA MENGGUNAKAN FASTER REGION-BASED CONVOLUTIONAL NEURAL NETWORK.

---

Penilaian

---

This research discusses four scenarios in developing a Faster Region-based Convolutional Neural Network (Faster R-CNN) model to detect bleeding in radiological images of the human brain. We specifically tested and compared key parameters, namely learning rate, batch size, backbone architecture, and data sharing, to determine the most effective configuration. The results show that the learning rate 0.001, batch size 4, ResNet-50 backbone and data split 90:10 are the best of the datasets used. These findings could provide a valuable basis for the development of more sophisticated medical detection applications, with the hope of improving the diagnosis and treatment of brain hemorrhage sufferers more effectively.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307006453	T131234	T1312342023	Central Library (Referens)	Available

Detail Information

Series Title

-

Call Number

T1312342023

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2023

Collation

xviii, 72 hlm.; ilus.;29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

004.07

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
Pemrosesan Data Elektronik

Specific Detail Info

-

Statement of Responsibility

MURZ

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment